© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 80489
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant consequences or impact related to loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wdx
    -0.08
    èģĶç½ij
    -0.07
    inch
    -0.06
    elope
    -0.06
    reo
    -0.06
    uci
    -0.06
    unei
    -0.06
     migrationBuilder
    -0.06
    ourcem
    -0.06
    ëŀij
    -0.06
    POSITIVE LOGITS
     when
    0.09
     When
    0.07
    quam
    0.06
    when
    0.06
    keiten
    0.06
    ãģĭãģ®
    0.06
    apus
    0.06
    When
    0.06
     abdom
    0.06
    .documentation
    0.05
    Activations Density 0.049%

    No Known Activations